Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7988
    Prev
    Next
    INDEX
    Explanations

    references to dolls

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dolls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EED
    -0.81
    TAIN
    -0.74
    ãĥ¥
    -0.72
    NING
    -0.68
    GGGGGGGG
    -0.65
    RAW
    -0.64
    riott
    -0.64
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.61
     forc
    -0.61
     Unified
    -0.61
    POSITIVE LOGITS
     doll
    1.10
     dolls
    1.07
    maker
    0.95
    wright
    0.87
    ophone
    0.82
     Doll
    0.80
    endor
    0.78
     figur
    0.77
    oru
    0.76
    makers
    0.76
    Activations Density 0.019%

    No Known Activations